© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114525
    Prev
    Next
    INDEX
    Explanations

    paintballs, water games, rocket contest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heroin
    -0.12
    drug
    -0.11
     drug
    -0.11
    coffee
    -0.11
     coffee
    -0.10
     Knife
    -0.10
     Pey
    -0.09
     Drug
    -0.09
     Candle
    -0.09
     cigaret
    -0.09
    POSITIVE LOGITS
     muddy
    0.16
     soaked
    0.16
     Foam
    0.15
     squirt
    0.15
     foam
    0.15
     hose
    0.14
     slime
    0.14
     vat
    0.14
     water
    0.13
     soak
    0.13
    Activations Density 0.112%

    No Known Activations